Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 65k
    5. 4-GEMMASCOPE-MLP-65K
    6. 60
    Prev
    Next
    INDEX
    Explanations

    references to online services or digital platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.73
     وتسجيلات
    -0.71
     Normdatei
    -0.67
    Билгалдахарш
    -0.67
    存于互联网档案馆
    -0.66
    virons
    -0.63
    Lähteet
    -0.62
    Độ
    -0.61
    atedral
    -0.61
     cref
    -0.61
    POSITIVE LOGITS
     Cric
    0.49
    ưu
    0.49
    __((
    0.48
    autique
    0.47
    Reference
    0.44
    >("
    0.43
     Prak
    0.42
    reference
    0.42
    Cot
    0.41
    ern
    0.41
    Activations Density 0.108%

    No Known Activations